© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57382
    Prev
    Next
    INDEX
    Explanations

    safety incidents and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     et
    0.57
    ليم
    0.48
    ex
    0.45
    @
    0.45
    番
    0.44
     created
    0.43
    少量
    0.43
    5
    0.42
     matter
    0.41
     selected
    0.41
    POSITIVE LOGITS
     항상
    0.52
     Eurostile
    0.52
     مشرقی
    0.50
     чемпиона
    0.48
     언제
    0.47
    ॉइड
    0.47
    iend
    0.46
    大多數
    0.46
     endearing
    0.46
     perspiration
    0.46
    Activations Density 0.001%

    No Known Activations